Title :
Motion description with local binary pattern and motion history image: Application to human motion recognition
Author :
Guo, Ping ; Miao, Zhenjiang
Author_Institution :
Inst. of Inf. Sci., Beijing Jiaotong Univ., Beijing
Abstract :
This paper presents a new human motion recognition method based on motion history image (MHI) and local binary pattern (LBP). MHI describes human motion sequence in one gray level image and LBP extracts its texture features. LBP feature image is built and chi square distance is applied to compute matching cost. Experiments are conducted with encouraging results which show a success of applying LBP in motion recognition.
Keywords :
feature extraction; image matching; image motion analysis; image sequences; image texture; chi square distance; gray level image; human motion recognition; human motion sequence; image matching cost; local binary pattern; motion description; motion history image; texture feature extraction; Data mining; Face recognition; Feature extraction; History; Humans; Image recognition; Image sequences; Pattern recognition; Pixel; Spatiotemporal phenomena; local binary pattern; motion history image; motion recognition;
Conference_Titel :
Haptic Audio visual Environments and Games, 2008. HAVE 2008. IEEE International Workshop on
Conference_Location :
Ottawa, Ont.
Print_ISBN :
978-1-4244-2668-3
Electronic_ISBN :
978-1-4244-2669-0
DOI :
10.1109/HAVE.2008.4685319
